Structured data such as tabular data, time series and graphs powers many core data mining applications including recommendation, forecasting and user behavior analysis. Conventional approaches such as statistical models, classical machine learning methods and deep neural networks have achieved strong results. Yet most methods are designed for a single task or dataset and lack the ability to generalize across diverse structured data problems. Recent advances in foundation models point to a new direction for structured data modeling. Inspired by progress in natural language processing and computer vision, emerging research explores large-scale pretraining, synthetic data generation and in-context learning (ICL) to build more general-purpose models. In particular, tabular foundation models provide a promising path toward unifying heterogeneous structured modalities. This perspective treats tables as a common representation that can capture information from tabular data, time series, and graphs within a shared learning framework. Early studies show encouraging capabilities including cross-task generalization, few-shot adaptation and knowledge transfer across datasets. This tutorial presents a systematic overview of this emerging paradigm. We review classical foundations, introduce recent tabular foundation models, and discuss key challenges in pretraining data generation, model design, and multi-task learning.
Tsinghua University
Tsinghua University
Nanjing University
Hong Kong University of Science and Technology (Guangzhou)
Stable Al Technology Co., Ltd.
Introduction & Motivation
Fundamentals of Tabular Modeling
Advances of Tabular Foundation Models
Cross-Modality Modeling Learning
Open Problems & Future Directions
If you find this tutorial useful, please consider citing:
@inproceedings{cui2026toward,
title={Toward Generalist Models for Structured Data: Fundamentals, Emerging Trends and Applications},
author={Cui, Peng and Zhang, Xingxuan and Ye, Han-Jia and Chen, Jintai and Li, Shuyang},
booktitle={Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V. 2},
pages={13304--13307},
year={2026}
}
For any questions regarding this tutorial, please reach out to Shuyang Li via lsy5215212@outlook.com